SEARCH · PubMed Health

Results for “Linear Models”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 973 records · Page 54Linked to original sources

PubMed1998

Late complications after postoperative radiotherapy in endometrial cancer: analysis of 317 consecutive cases with application of linear-quadratic model.

PURPOSE: To evaluate the incidence and risk factors for late complications after postoperative radiotherapy in endometrial cancer patients. METHODS AND MATERIAL: We performed a detailed retrospective analysis of 317 endometrial cancer patients given postoperative radiotherapy. A total of 247 patients (78%) received both intracavitary (BRT) and external beam irradiation (XRT); 49 patients (15%) received only BRT, and 21 (7%) only XRT. BRT included radium (Ra) and cesium (Cs). The mean dose rate for both isotopes at 0.5 cm from the applicator surface was 0.47 +/- 0.06 and 1.42 +/- 0.41 Gy/h, and the mean total dose was 50.5 +/- 10.3 and 48.4 +/- 15.0 Gy, respectively. Mean BRT dose at 0.5 cm was 50.1 +/- 11.7 Gy (range 14.5-71.0). Mean XRT dose in the International Commission on Radiation Units and Measurements (ICRU) reference point was 49.0 +/- 3.7 Gy (range 22.0-66.0) given in fractions of 1.54-2.49 Gy (mean 2.0 +/- 0.17) with a two- or four-field technique. Follow-up ranged from 4 to 21 years (median 7.3). Normalized total dose (NTD) including XRT and BRT doses was calculated based on a linear quadratic equation. RESULTS: Five-year overall survival rate was 75%, and 5-year disease-free survival (censored for noncancer deaths) was 81%. Late radiotherapy complications of any grade occurred in 158 patients (51%), including bowel complications in 41% and urinary bladder complications in 21%. A total of 37 grade 3 or 4 complications were observed in 33 patients (11%), of whom 32 were treated with both XRT and BRT. Severe bowel and/or urinary bladder complications occurred in 24 patients: in 14 of 72 patients (19.4%) who received XRT and Cs BRT, and in 10 of 172 patients (6.0%) applied XRT and Ra BRT. The higher proportion of severe bowel and/or bladder complications in the former group was due to the particularly frequent rate of these events (30.0%) in a subset of 47 patients who received XRT combined with Cs BRT at the dose rate of 1.7 Gy/h and the total BRT dose of 60 Gy. Higher NTD, XRT fraction dose, BRT dose rate, Cs BRT, two-field XRT technique, short overall radiotherapy time, and older age were correlated with increased late-event risk in univariate analysis. Multivariate Cox analysis demonstrated that the independent risk factors for late bowel complications were NTD (p = 0.000) and BRT dose rate (p = 0.036), whereas for bladder complications they were BRT dose rate (p = 0.005) and XRT fraction dose (p = 0.041). Neither clinical factor (age, parity, prior abdominal surgery, FIGO stage, diabetes mellitus, or hypertension) nor the surgery-to-radiotherapy interval, nor overall radiotherapy time was independently associated with the risk of late bladder or bowel complications. CONCLUSIONS: The risk of late complications after postoperative radiotherapy in endometrial cancer depends mainly on treatment-related factors: NTD, BRT dose rate, and XRT fraction dose. The use of combined XRT and BRT increases the risk of late effects. NTD calculations including BRT dose rate and XRT fraction dose enable estimation of radiobiologically equivalent dose and can decrease the risk of mistakes when the radiotherapy regimen is changed.

Actuarial Analysis↗

PubMed2000

Properties of added variable plots in Cox's regression model.

The added variable plot is useful for examining the effect of a covariate in regression models. The plot provides information regarding the inclusion of a covariate, and is useful in identifying influential observations on the parameter estimates. Hall et al. (1996) proposed a plot for Cox's proportional hazards model derived by regarding the Cox model as a generalized linear model. This paper proves and discusses properties of this plot. These properties make the plot a valuable tool in model evaluation. Quantities considered include parameter estimates, residuals, leverage, case influence measures and correspondence to previously proposed residuals and diagnostics.

Biometry↗

PubMed1998

Concentration-effect relationship of l-propranolol and metoprolol in spontaneous hypertensive rats after exercise-induced tachycardia.

The concentration-effect relationship of l-propranolol and dl-metoprolol were investigated in spontaneous hypertensive rats using reduction in exercise-induced tachycardia as a pharmacodynamic endpoint. The influence of protein binding on the effect relationship was also assessed. The rats were assigned to treatment or placebo groups, where each group received three randomly selected consecutively increasing steady-state infusions. Different pharmacodynamic effect models were fitted to the data, using nonlinear mixed effect modeling. The data were best described by a combined effect model, with a sum of an ordinary Imax and a linear model. At the lower concentration range, the ordinary Imax model dominated, although at higher concentrations, the effect was linearly related to the antagonist concentration. The Imax were 83 +/- 6 and 103 +/- 6 beats . min-1 and the IC50 were 18.1 +/- 4.3 and 50.6 +/- 15.2 ng/ml for l-propranolol and dl-metoprolol, respectively. The slope in the linear model was steeper for l-propranolol than for dl-metoprolol, 28.9 +/- 2.8 and 4.48 +/- 0.39 beats . ml . (min . microgram)-1, respectively. Plasma protein binding of l-propranolol was saturable. The unbound IC50 for l-propranolol was 1.14 +/- 0.27 ng/ml. The concentration-effect relationship of l-propranolol was altered at higher plasma concentrations, due to saturable protein binding. The Imax and the linear concentration-effect relationship may be interpreted as a specific beta-antagonist effect and a membrane-stabilizing effect, respectively. Using exercise-induced tachycardia as a pharmacodynamic endpoint, to study the effect of beta-antagonists in spontaneous hypertensive rats, seems to give reliable results and can be a useful model to extrapolate to humans.

Adrenergic beta-Antagonists↗

PubMed2006

Dispersion frailty models and HGLMs.

In medical research recurrent event times can be analysed using a frailty model in which the frailties for different individuals are independent and identically distributed. However, such a homogeneous assumption about frailties could sometimes be suspect. For modelling heterogeneity in frailties we describe dispersion frailty models arising from a new class of models, namely hierarchical generalized linear models. Using the kidney infection data we illustrate how to detect and model heterogeneity among frailties. Stratification of frailty models is also investigated.

Adult↗

PubMed1996

Screening of vibroarthrographic signals via adaptive segmentation and linear prediation modeling.

This paper proposes a noninvasive method to diagnose chondromalacia patella at its early stages by recording knee vibration signals (also known as vibroarthrographic or VAG signals) over the mid-patella during normal movement. An adaptive segmentation method was developed to segment the nonstationary VAG signals. The least squares modeling method was used to reduce the number of data samples to a few model parameters. Model parameters along with a few clinical parameters and a signal variability parameter were then used as discriminant features for screening VAG signals by applying logistic and discriminant algorithms. The system was trained using ten normal and eight abnormal signals. It correctly screened a separate test set of ten normal and eight abnormal signals except for one normal signal. The proposed method should find use as an alternative technique for diagnosis of knee joint pathology or as a test before arthroscopy or major knee surgery.

Algorithms↗

PubMed1994

Characterization of the passive responses of live skeletal muscle using the quasi-linear theory of viscoelasticity.

The tensile viscoelastic responses of live, innervated rabbit skeletal muscle were measured and characterized using the quasi-linear model of viscoelasticity. The tibialis anterior (TA) and extensor digitorum longus (EDL) muscles of anesthetized New Zealand white rabbits were surgically exposed and tested under in vivo conditions. Rate sensitivity of the force-time history was observed in response to constant velocity testing at rates from 0.01 to 2.0 Hz. Average hysteresis energy, expressed as a percentage of maximum stored strain energy, was 39.3 +/- 5.4% and was insensitive to deformation rate. The quasi-linear model, with constants derived from relaxation testing, was able to describe and predict these responses with correlation exceeding the 99% confidence interval for the 132 constant velocity tests performed (rmean = 0.9263 +/- 0.0373). The predictive ability of this model was improved when compressive loading effects on the muscle were neglected, rmean = 0.9306 +/- 0.0324. The rate insensitivity of hysteresis energy was predicted by the model; however, the absolute value of the hysteresis was underestimated (30.2 +/- 4.0%). Both muscles demonstrated strikingly different elastic functions. Geometric normalization of these responses (stress and strain) did not result in a single elastic function capable of describing both muscles. Based on these results, the quasi-linear model is recommended for the characterization of the structural responses of muscle; however, further investigation is required to determine the influence of muscle geometry and fiber architecture on the elastic function.

Animals↗

PubMed2003

Inference for a linear regression model with an interval-censored covariate.

Interval-censored observations of a response variable are a common occurrence in medical studies, and usually result when the response is the elapsed time until some event whose occurrence is periodically monitored. In this paper we consider a multivariate regression setting in which the explanatory variable is interval censored. Use of an ad hoc method of analysis for such data, such as taking the midpoint of the interval-censored covariate and applying ordinary least-squares, is not in general valid. We develop a likelihood approach, together with a two-step conditional algorithm, to jointly estimate the regression coefficients as well as the marginal distribution of the covariate. The resulting estimators are asymptotically normal. The performance of the method is assessed via simulations, and illustrated using data from a recent HIV/AIDS clinical trial to assess the association between waiting time between indinavir failure and subsequent viral load at enrolment. Extensions of the procedure to other parametric distributions are discussed.

Adult↗

PubMed2006

Linear regression model for predicting patient-specific total skeletal spongiosa volume for use in molecular radiotherapy dosimetry.

UNLABELLED: The toxicity of red bone marrow is widely considered to be a key factor in restricting the activity administered in molecular radiotherapy to suboptimal levels. The assessment of marrow toxicity requires an assessment of the dose absorbed by red bone marrow which, in many cases, requires knowledge of the total red bone marrow mass in a given patient. Previous studies demonstrated, however, that a close surrogate-spongiosa volume (combined tissues of trabecular bone and marrow)-can be used to accurately scale reference patient red marrow dose estimates and that these dose estimates are predictive of marrow toxicity. Consequently, a predictive model of the total skeletal spongiosa volume (TSSV) would be a clinically useful tool for improving patient specificity in skeletal dosimetry. METHODS: In this study, 10 male and 10 female cadavers were subjected to whole-body CT scans. Manual image segmentation was used to estimate the TSSV in all 13 active marrow-containing skeletal sites within the adult skeleton. The age, total body height, and 14 CT-based skeletal measurements were obtained for each cadaver. Multiple regression was used with the dependent variables to develop a model to predict the TSSV. RESULTS: Os coxae height and width were the 2 skeletal measurements that proved to be the most important parameters for prediction of the TSSV. The multiple R(2) value for the statistical model with these 2 parameters was 0.87. The analysis revealed that these 2 parameters predicted the estimated the TSSV to within approximately +/-10% for 15 of the 20 cadavers and to within approximately +/-20% for all 20 cadavers in this study. CONCLUSION: Although the utility of spongiosa volume in estimating patient-specific active marrow mass has been shown, estimation of the TSSV in active marrow-containing skeletal sites via patient-specific image segmentation is not a simple endeavor. However, the alternate approach demonstrated in this study is fairly simple to implement in a clinical setting, as the 2 input measurements (os coxae height and width) can be made with either pelvic CT scanning or skeletal radiography.

Bone Marrow↗

PubMedDate not supplied

[Use of the linear-square model for evaluation of the distribution of equivalent doses of electron irradiation].

The differences between physical absorbed dose of the electron radiation and normalized up to the total dose, fractionated by daily dose equal to 2 Gy, corresponding to "equivalent biologic dose isobio Gy 2" have been analysed. The effect of the fraction dose on the distribution of equivalent total dose in relation to the localization of the neoplastic tumor in the irradiated area has been assessed. On account of the calculations it has been found that alike as in the case of photon radiation the application of fractionated doses equal or lower than 2 Gy is more safe for healthy tissues as compared with higher fractionated doses. No distinct differences have been present between the distribution of physical and biological doses for isodoses below 80%. This fact suggests that the choice of the energy of electron radiation should be decided on account of the depth of the neoplastic tumor and the distribution of physical dose--whereas the distribution of biologic isodoses (isobio Gy 2) of electron radiation is of significant importance in the estimation of the tolerance of critical organs situated in the area between skin and the irradiated tumor.

Cobalt Radioisotopes↗

PubMed2004

Phenomena leading to cell survival values which deviate from linear-quadratic models.

For several decades, the prevailing paradigm for modeling the effects of ionizing radiation (IR) on living systems was the target model with its inherent assumptions--that only those cells in the radiation path whose molecules sustained collisions with high energy particles and rays were damaged, that the damage was proportional to the energy absorbed by each cell and to the number of cells absorbing energy, and that all cells had identical sensitivities to radiation. However, evidence has accumulated that cells exhibit phenomena at low radiation exposures that appear to contradict at least one of these assumptions. Some of these phenomena currently under active study include low-dose hypersensitivity (HRS), increased radiation radioresistance (IRR), the adaptive response (AR), the bystander effect (BE), and death-inducing factor (DIE). These effects may interact to give rise to other phenomena such as hormesis, in which small amounts of otherwise toxic agent appear to be beneficial. Elucidating the cellular and molecular bases for these phenomena will lead to greater understanding of the relationships of these processes, including hormesis, to human health.

Animals↗

PubMed1997

Treatment-patient interactions for diagnostics of cross-over trials.

In cross-over trials, various types of responses may be recorded, not all of which can be appropriately modelled by a Normal distribution. Widening the class of models to the generalized linear model family has a number of advantages. An important one is that certain interactions, especially that between patients and treatments, can easily be fitted for frequency and count data. These can be used as diagnostics for the fit of the model used. One handicap has been the frequentist difficulty of comparing the fit of different non-nested models in this family. This can be overcome by the use of a model selection criterion such as the Akaike or Bayesian information criterion. This approach to modelling and diagnostics for cross-over trials is applied to two studies involving small counts of anginal attacks, previously analysed in the literature using classical Normal techniques.

Clinical Trials as Topic↗

PubMed1997

Evaluating the goodness of fit in models of sparse medical data: a simulation approach.

BACKGROUND: Epidemiological studies of rare events, which are common in the medical literature, often involve modeling sparse data sets. Assessing the fit of these models may be complicated by the large numbers of observed zeros in the data set. METHODS: Poisson models, fitted as generalized linear models, were used to investigate the referral patterns of patients suffering from end-stage renal failure in south west Wales. The usual method for assessing the goodness of fit is to compare the deviance with a chi 2 distribution with appropriate degrees of freedom. However, this test may be invalid when the data set is sparse, as the deviance values may be unusually low compared to the degrees of freedom. This would suggest that there is a problem with underdispersion when, in fact, the large numbers of zeros in the data set make the comparison with the chi 2 distribution unreliable. A simulation approach is advocated as an alternative method of assessing model fit in these situations. RESULTS: Three models are considered in detail here. The first modelled the total referrals in each of the 245 wards in the study area and included two explanatory variables. These observations were not unusually sparse and both the chi 2 goodness of fit test and the simulation methodology outlined here suggested that the model did not fit. The second model included the population 'at risk' as an offset and the model improved considerably. Both the chi 2 test and the simulation approach suggested that this model did fit. Finally, the data were disaggregated into five age groups providing 1225 observations and a very sparse data set. According to the chi 2 goodness of fit test, the deviance was very low suggesting that the model was underdispersed. Using simulated data, it was shown that the deviance was not unusually low and that the model fitted the data reasonably well. CONCLUSION: In cases where the data set being modelled is sparse, it is useful to test the goodness of fit of a Poisson model using a simulation approach, rather than relying on the chi 2 test.

Adolescent↗

PubMed1996

A comparison of statistical methods for clustered data analysis with Gaussian error.

We investigate by simulation the properties of four different estimation procedures under a linear model for correlated data with Gaussian error: maximum likelihood based on the normal mixed linear model; generalized estimating equations; a four-stage method, and a bootstrap method that resamples clusters rather than individuals. We pay special attention to the group randomized trials where the number of independent clusters is small, cluster sizes are big, and the correlation within the cluster is weak. We show that for balanced and near balanced data when the number of independent clusters is small (< or = 10), the bootstrap is superior if analysts do not want to impose strong distribution and covariance structure assumptions. Otherwise, ML and four-stage methods are slightly better. All four methods perform well when the number of independent clusters reaches 50.

Bias↗

PubMed2001

BJ: an S-Plus program to fit linear regression models to censored data using the Buckley-James method.

Most researchers are familiar with ordinary multiple regression models, most commonly fitted using the method of least squares. The method of Buckley and James (J. Buckley, I. James, Linear regression with censored data, Biometrika 66 (1979) 429-436.) is an extension of least squares for fitting multiple regression models when the response variable is right-censored as in the analysis of survival time data. The Buckley-James method has been shown to have good statistical properties under usual regularity conditions (T.L. Lai, Z. Ying, Large sample theory of a modified Buckley-James estimator for regression analysis with censored data, Ann. Stat. 19 (1991) 1370-1402.). Nevertheless, even after 20 years of its existence, it is almost never used in practice. We believe that this is mainly due to lack of software and we describe here an S-Plus program that through its inclusion in a public domain function library fully exploits the power of the S-Plus programming environment. This environment provides multiple facilities for model specification, diagnostics, statistical inference, and graphical depiction of the model fit.

Data Interpretation, Statistical↗

PubMed1995

Simple modelling of linear and nonlinear mechanical responses to sinusoidal oscillations during muscle contraction.

The mechanical responses of muscle to sinusoidal oscillations were analysed using a contraction model based on Huxley's 1957 model. To reproduce the three well-documented exponential processes resolved in the course of sinusoidal analysis, a few modifications had to be made on the original Huxley's model: (1) Each myosin cross-bridge should support substantial force at its position where the rate of detachment (g) abruptly changes. (2) Each cross-bridge should have the capability of stress-relaxation while attached to actin. This stress-relaxation should occur with a rate constant greater than the overall turnover rate of cross-bridges. After these modifications, the model reproduces not only the three exponential processes, but also the nonlinearity in the mechanical response, which is derived from the asymmetrical dependence of the rate constants on the cross-bridge strain. The present study provides a simplest model which reproduces the linear and nonlinear responses to sinusoidal oscillations, and help relate the exponential processes to the underlying attachment/detachment steps in the cross-bridge cycle.

Animals↗

PubMed2001

Effects of covariance model assumptions on hypothesis tests for repeated measurements: analysis of ovarian hormone data and pituitary-pteryomaxillary distance data.

In the analysis of repeated measurements, multivariate methods which account for the correlations among the observations from the same experimental unit are widely used. Two commonly-used multivariate methods are the unstructured multivariate approach and the mixed model approach. The unstructured multivariate approach uses MANOVA types of models and does not require assumptions on the covariance structure. The mixed model approach uses multivariate linear models with random effects and requires covariance structure assumptions. In this paper, we describe the characteristics of tests based on these two methods of analysis and investigate the performance of these tests. We focus particularly on tests for group effects and parallelism of response profiles.

Adolescent↗

PubMed2004

Analysis of the EEG-fMRI response to prolonged bursts of interictal epileptiform activity.

The use of combined EEG-fMRI to study interictal epileptiform activity is increasing and has great potential as a clinical tool, but the haemodynamic response to epileptiform activity remains incompletely characterised. To this end, 19 data sets from 14 patients with prolonged bursts of focal or generalised interictal epileptiform activity lasting up to 15 s were analysed. To determine whether the inclusion of the durations of the epileptic events in the general linear model resulted in increased statistical significance of activated regions, statistical maps were generated with and without the event durations. The mean differences when including the durations were a 14.5% increase in peak t value and a 29.5% increase in volume of activation. This suggests that when analysing EEG-fMRI data from patients with prolonged bursts of interictal epileptiform activity, it is better to include the event durations. To determine whether the amplitudes and latencies of the measured responses were consistent with the general linear model, the haemodynamic response functions for bursts of different durations were calculated and compared with the model predictions. The measured amplitude of the response to the shortest duration events was consistently larger than predicted, which is consistent with studies in normal subjects. For the two data sets with the widest range of event durations, the measured amplitudes increased with the durations of the events without evidence of the plateau that was expected from the general linear model. There were no consistent differences between the measured and modelled latencies.

Adolescent↗

PubMed2004

Evaluating factors that influence microbial phenanthrene biodegradation rates by regression with categorical variables.

To advance the accuracy of bioremediation measurements, it is useful before specific experiments to attribute or estimate the influence of both experimental as well as field conditions on the expected magnitudes of microbial degradation rate coefficients. This paper analyzes the numerical contribution, or influence, of categories of conditions, such as bacterial adaptive state, electron acceptor type, mixing, generalized sorption conditions, and biodegradation temperature, on published phenanthrene biodegradation rates as an example of our regression approach. A fundamental microbial degradation rate equation is transformed to an additive model, then using multiple linear regression on published data, coefficients (of categorical variables) and a linear model are presented that estimate first-order biodegradation rate coefficients to within a factor of 3. Numerical estimates of how much bacterial adaptive state and presence of a sorption phase, the two most statistically significant factors, alter the phenanthrene biodegradation rate are presented. The influence of some measurement or field conditions, for example, the influence of oxygen reduction versus optimal nitrate reduction, cannot be distinguished statistically given the available data and range. The regression model is tested using conditions from newly published papers to estimate a priori the expected rate, which compares very favorably to measurements reported in the papers. Due to limited published data and range for extreme cases, the current coefficients do not apply to degradation of very aged phenanthrene nor very low concentrations of electron acceptors. As estimating tools, however, the coefficients themselves and the regression approach have very beneficial roles in design of experiments for both laboratory and field settings. Our method can be applied to other PAHs as sufficient data become available.

Adsorption↗